Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agents

2026-08-18

AI Summary

该论文提出使用EvalXRL基准，通过解释性强化学习方法帮助诊断和修复强化学习代理中的故障的有效性来评估这些方法。

Abstract

This preliminary paper outlines a planned evaluation benchmark for Explainable Reinforcement Learning (XRL) methods. Current evaluations rely on functionally-grounded metrics like faithfulness and compactness, and on human-grounded proxies like subjective ratings or prediction accuracy. We suggest evaluating XRL methods by how effectively their generated explanations help to diagnose and fix malfunctioning reinforcement learning (RL) agents. We propose EvalXRL, a benchmark in which a Large Language Model (LLM) coding agent uses different XRL methods to diagnose a held-out malfunction in an RL agent, and then repair it. Our proposed benchmark iterates across (environment $\times$ malfunction $\times$ XRL method) tuples and uses the reward signal of the RL agents to form a final score for each XRL method. The coding agent may use the method interactively: invoke the XRL method, process its output, form new hypotheses on what is broken, and invoke the method again with parameters adjusted for testing these hypotheses. This closed-loop structure may be described as a simplified version of the scientific method. Some XRL methods provide self-evaluations that follow this pattern; we propose the first head-to-head comparison of multiple XRL methods in closed-loop usage.

Problem

• Explainable Reinforcement Learning
• Evaluation Benchmark
• Diagnose and Fix
• Malfunctioning Agents
• Large Language Model

Innovation

• Explainable Reinforcement Learning
• Large Language Model
• Closed-Loop Evaluation
• Agent Repair
• Benchmark